Author

Joshua Smith

h-index 1 View on Semantic Scholar

We have 1 of 2 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Points2Reward: Robotic Manipulation Rewards from Just One Video

P2R tracks task-relevant object points in task demonstrations and policy rollouts, and matches them to compare the desired and achieved object trajectories to generate reward scores, which effectively computes dense rewards from a single video.

Junyao Shi, Joshua Smith, Jia-Ning Qian et al. · 6 citations